INDEX

Explanations

phrases indicating ongoing actions or experiences related to duration and continuity

oai_token-act-pair · gpt-4o-mini Triggered by @bot

"been" followed by an "-ing" verb

np_acts-logits-general · gemini-2.0-flash

has been doing

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verwijspagina

-0.41

msgTypes

-0.40

躇

-0.38

ایناق

-0.37

elemField

-0.37

featureID

-0.36

描いた

-0.36

QMetaType

-0.36

zak

-0.35

Jon

-0.34

POSITIVE LOGITS

queryInterface

0.58

 existed

0.49

 existir

0.47

 existência

0.46

存在的

0.46

 hivat

0.46

endphp

0.45

 estuvo

0.45

 existence

0.45

Véxase

0.45

Activations Density 0.138%

phrases indicating ongoing actions or experiences related to duration and continuity

"been" followed by an "-ing" verb

has been doing

No Comments

No Known Activations